© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 822
    Prev
    Next
    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.81
     שוליים
    -0.81
     تضيفلها
    -0.81
     wireType
    -0.79
    帖最后由
    -0.78
     متعلقه
    -0.75
    Παραπομπές
    -0.73
     Normdatei
    -0.72
     unknownFields
    -0.72
     typelib
    -0.71
    POSITIVE LOGITS
    2
    0.58
    5
    0.54
    3
    0.51
    8
    0.50
     d
    0.50
    6
    0.50
    O
    0.49
    9
    0.47
     O
    0.47
    P
    0.47
    Activations Density 0.002%

    No Known Activations